Esker, a global cloud platform and leader in AI-driven process automation solutions for Finance, Procurement and Customer Service functions, announced the issuance of U.S. Patent No. 11631265 by the U.S. Patent and Trademark Office (USPTO) for Esker’s machine learning technology.
Latest Fintech Interview: Global Fintech Interview with Peter Barcak, CEO and Co-Founder at credolab
“One of the strengths of Esker’s solution is to naturally solve all the complexity of receiving thousands of orders in different formats and with a myriad of different characteristics and particularities”
Spanning both the source-to-pay (S2P) and order-to-cash (O2C) cycles, Esker’s AI-powered solutions are built to vastly reduce repetitive and low-value tasks. The patented technology addresses the need for accurate automated data extraction on incoming documents. For businesses with a large customer base, keying information in manually for invoices, orders and other documents is time-consuming and expensive.
Esker’s newly patented AI technology uses traditional and machine learning algorithms to identify data fields, make routing decisions and suggest next actions with the goal of reducing the number of touches during processing as much as possible. The data is read from a document and the AI creates rules that define what data to retrieve and in which format. Through user input, these rules are adapted and the accuracy of the extraction process increases over time. This interplay of AI technology and human supervision reduces mindless and error-prone manual data entry down to almost zero.
The efficacy of Esker’s technology can be witnessed in the order management process. For example, each customer likely uses a different template for their purchase orders (POs) or even changes their layout occasionally. Capturing data from customer orders no matter the channel, format or layout they arrive in, AI retrieves the relevant information on both the header and line-item levels, such as shipping address, PO number, product references, quantities and prices. The machine learning technology then learns from user corrections, increasing the recognition rates after only a few adjustments. “One of the strengths of Esker’s solution is to naturally solve all the complexity of receiving thousands of orders in different formats and with a myriad of different characteristics and particularities,” said Gervasio Prieto, Customer Service Manager at CAPSA Food, an Esker customer. This technology does not only apply to order recognition in Esker’s Customer Service solution suite, but also to vendor invoices, remittances and deduction claims.
Read More About Fintech Interview: Global Fintech Interview with Brian Duncan, President at me&u
Esker has been steadily investing in R&D for utilizing AI capabilities in all its solutions for nearly 20 years now. Already at the forefront of AI technology when this patent application was submitted 12 years ago, auto learning is still used in Esker’s solutions today. This technology was expanded on with additional layers of deep learning neural networks.
“When we started on the AI journey at Esker, we focused our efforts on data extraction in order to decrease manual data entry for incoming invoices and orders,” said Jean-Jacques Bérard, Vice President of Research and Development at Esker. “This project has expanded to enriching the extracted data with predictive and prescriptive functionalities such as detecting anomalies in orders, predicting the invoice analytical axis, or proposing an answer to a customer request. This combination of human and artificial intelligence allows for making the work more engaging and efficient.”
Browse The Complete Interview About Fintech : Global Fintech Interview with Greg Oslan, CEO at Arturo
[To share your insights with us, please write to sghosh@martechseries.com]
